DR. GERO / THE MODEL LAB
Illustrative workflow01 / 07
DEFINE YOUR TASK

Create a leaderboard

Describe your task and choose how to score the answers.

6 sec
New leaderboardWorkspace / Create

Start with one real task.

Leaderboard name
What should the model do?
How will you score the answers?
Exact matchLLM judgeHuman review
Every comparison starts with the same task.Create leaderboard
Leaderboard created
0:00 / 0:57

Initial model names and metrics reproduce a reference ranking; * costs and derived value ratios may include estimates. The workflow, 1,000-model catalog and later ranking changes are illustrative. Jobs are compressed; you approve candidate changes. Fine-tuning is optional.

Space play / pause   ← → steps

The seven steps, in words
  1. Create a leaderboardDefine your task and choose exact match, an LLM judge or human evaluation.
  2. Connect your agent’s I/OSend input/output examples through the API or import a Hugging Face dataset. Supply or review reference answers.
  3. Auto SelectNarrow an illustrative catalog of 1,000 models to the five shown in the supplied ranking. Your task, cost and latency preferences guide selection.
  4. Rank the leaderboardEvaluate candidates on the same examples and compare quality, cost and response time.
  5. Serve one endpointConnect your application to a stable private API. Choose an eligible winner, a pinned model or a balanced routing mix.
  6. Fine-tune a modelOptionally train on curated examples. Evaluate the new version on held-out data and review it before adding or serving it.
  7. Keep the ranking currentSchedule re-evaluation as data changes. Approve new candidates and remove others from the comparison. The five-model ranking evolves while your application’s endpoint stays the same.